This disclosure relates generally to detection of mild cognitive impairments in subjects. The method and system proposed provides a continuous/seamless monitoring platform for MCI detection in subjects by continuously monitoring routine activities of subjects (Activities of Daily Living (ADL)) in a smart environment using plurality of passive, unobtrusive, binary, unobtrusive non-intrusive sensors embedded in living infrastructure. The proposed method and system detects symptoms of MCI at the onset of the disease, while also addressing issue of sensor failures that causes gaps in the data. The collected sensor data is pre-processed in several stages which includes which includes pre-processing of sensor data, behavior deviation detection, and abnormality detection and so on. Further, the disclosure also proposes an autoencoder based technique, to reduce the dimension of the data to find personalized deviations in behavior of a subject which is used to detect if a subject could be a potential case of MCI.
Legal claims defining the scope of protection, as filed with the USPTO.
2. The processor implemented method of claim 1, wherein the step of optimizing, by using an auto encoder, size of the semantic vector representation of the corrected sensor data to generate an optimized vector data comprises: applying a dimension reduction based window sizing technique on the semantic vector representation of the corrected sensor data.
3. The processor implemented method of claim 1, further comprising upon detecting behavior deviation of the subject, analyzing the semantic vector representation corresponding to the optimized vector data and performing a comparison of the analyzed semantic vector representation with a previous adjacent semantic vector representation; and storing a start time and an end time specific to the behavior deviation of the subject in the database.
4. The processor implemented method of claim 3, further comprising analyzing one or more corresponding sub-vectors based on the start time and the end time specific to the behavior deviation of the subject; and tagging the analyzed one or more corresponding sub-vectors as one or more abnormal vectors.
5. The processor implemented method of claim 4, further comprising detecting one or more random activities between the start time and the end time; and generating a flag indicative of an abnormal behavior when duration of the one or more repeated random activities is less than or greater than an actual duration of a corresponding particular activity.
6. The processor implemented method of claim 1, further comprising performing a Principal Component Analysis (PCA) on the behavior deviation of the subject detected for the specific time interval to obtain a set of eigen vectors based on a variance for the behavior deviation; and computing a personal variation index based on the set of eigen vectors.
7. The processor implemented method of claim 6, further comprising performing a comparison of the personal variation index with a pre-defined threshold; and flagging behavior of the subject as an abnormal behavior based on the comparison.
9. The system of claim 8, wherein the step to optimize the size of the semantic vector representation of the corrected sensor data is optimized to generate the optimized vector data by applying a dimension reduction based window sizing technique on the semantic vector representation of the corrected sensor data.
10. The system of claim 8, wherein the one or more hardware processors are further configured to, analyze, upon detecting behavior deviation of the subject, the semantic vector representation corresponding to the optimized vector data and perform a comparison of the analyzed semantic vector representation with a previous adjacent semantic vector representation, and store a start time and an end time specific to the behavior deviation of the subject in the database.
11. The system of claim 10, wherein the one or more hardware processors are further configured to analyze one or more corresponding sub-vectors based on the start time and the end time specific to the behavior deviation of the subject; and tag the analyzed one or more corresponding sub-vectors as one or more abnormal vectors performed.
12. The system of claim 11, wherein the one or more hardware processors are further configured to detect one or more random activities between the start time and the end time; and generate a flag indicative of an abnormal behavior when duration of the one or more repeated random activities is less than or greater than an actual duration of a corresponding particular activity.
13. The system of claim 8, wherein the one or more hardware processors are further configured to perform a Principal Component Analysis (PCA) on the behavior deviation of the subject detected for the specific time interval to obtain a set of eigen vectors based on a variance for the behavior deviation; and compute a personal variation index based on the set of eigen vectors.
14. The system of claim 13, wherein the one or more hardware processors are further configured to perform a comparison of the personal variation index with a pre-defined threshold; and flag behavior of the subject as an abnormal behavior based on the comparison.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
October 10, 2018
September 20, 2022
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.